© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1326
    Prev
    Next
    INDEX
    Explanations

    phrases involving "set" and its variations indicating preparation or arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "set" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    set up, set forth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.85
    Erreferentziak
    -0.73
     ویکی‌پدیای
    -0.72
     Réponses
    -0.67
    addPreferredGap
    -0.64
     Regularly
    -0.62
     mouseClicked
    -0.60
     विश्वसनीयता
    -0.60
     présidenti
    -0.58
    htdocs
    -0.58
    POSITIVE LOGITS
     aside
    1.04
     ablaze
    0.76
     forth
    0.75
     alight
    0.74
     precedent
    0.73
     precedents
    0.71
    aside
    0.68
     setting
    0.67
     sights
    0.66
     Setting
    0.64
    Activations Density 0.085%

    No Known Activations